EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model.
Yifu YuanJianye HaoFei NiYao MuYan ZhengYujing HuJinyi LiuYingfeng ChenChangjie FanPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- machine learning
- experimental data
- computational model
- theoretical analysis
- neural network model
- objective function
- input data
- unsupervised manner
- prediction model
- dynamical systems
- statistical model
- mathematical model
- em algorithm
- supervised learning
- probability distribution
- learning process
- video sequences
- bayesian networks
- image sequences
- decision making
- genetic algorithm